Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6061 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8389. Min Range: -7.8389
Max Act: 7.8389. Min Act: -0.1700
Data Index: 3879877 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8389. Min Range: -7.8389
Max Act: 7.6514. Min Act: -0.1700
Data Index: 3062829 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8389. Min Range: -7.8389
Max Act: 7.6514. Min Act: -0.1700
Data Index: 921185 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8389. Min Range: -7.8389
Max Act: 7.5264. Min Act: -0.1700
Data Index: 3648639 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8389. Min Range: -7.8389
Max Act: 7.4014. Min Act: -0.1700
Data Index: 7319559 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8389. Min Range: -7.8389
Max Act: 7.3389. Min Act: -0.1700
Data Index: 4265702 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8389. Min Range: -7.8389
Max Act: 7.3076. Min Act: -0.1700
Data Index: 4229308 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8389. Min Range: -7.8389
Max Act: 7.3076. Min Act: -0.1700
Data Index: 2603913 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8389. Min Range: -7.8389
Max Act: 7.2139. Min Act: -0.1700
Data Index: 8025504 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8389. Min Range: -7.8389
Max Act: 7.1514. Min Act: -0.1700
Data Index: 6020280 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8389. Min Range: -7.8389
Max Act: 7.1514. Min Act: -0.1700
Data Index: 8544398 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8389. Min Range: -7.8389
Max Act: 7.0889. Min Act: -0.1700
Data Index: 524588 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8389. Min Range: -7.8389
Max Act: 7.0889. Min Act: -0.1700
Data Index: 1544347 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8389. Min Range: -7.8389
Max Act: 7.0576. Min Act: -0.1700
Data Index: 3958002 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8389. Min Range: -7.8389
Max Act: 7.0576. Min Act: -0.1700
Data Index: 7726329 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8389. Min Range: -7.8389
Max Act: 7.0889. Min Act: -0.1700
Data Index: 4997759 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8389. Min Range: -7.8389
Max Act: 6.9951. Min Act: -0.1700
Data Index: 3052043 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8389. Min Range: -7.8389
Max Act: 7.0264. Min Act: -0.1700
Data Index: 8554621 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8389. Min Range: -7.8389
Max Act: 6.9326. Min Act: -0.1700
Data Index: 4997761 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8389. Min Range: -7.8389
Max Act: 6.9639. Min Act: -0.1700
Data Index: 5162159 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19